Music Genre Classification Research Articles

Automatic Music Genres Classification using Machine Learning

Classification of music genre has been an inspiring job in the area of music information retrieval (MIR). Classification of genre can be valuable to explain some actual interesting problems such as creating song references, finding related songs, finding societies who will like that specific song. The purpose of our research is to find best machine learning algorithm that predict the genre of songs using k-nearest neighbor (k-NN) and Support Vector Machine (SVM). This paper also presents comparative analysis between k-nearest neighbor (k-NN) and Support Vector Machine (SVM) with dimensionality return and then without dimensionality reduction via principal component analysis (PCA). The Mel Frequency Cepstral Coefficients (MFCC) is used to extract information for the data set. In addition, the MFCC features are used for individual tracks. From results we found that without the dimensionality reduction both k-nearest neighbor and Support Vector Machine (SVM) gave more accurate results compare to the results with dimensionality reduction. Overall the Support Vector Machine (SVM) is much more effective classifier for classification of music genre. It gave an overall accuracy of 77%.

Collaborative SVM classification in scale-free peer-to-peer networks

Distributed classification in large-scale P2P networks has gained relevance in recent years and support applications like distributed intrusion detection in P2P monitoring environments, online match-making, personalized information retrieval, distributed document classification in a P2P media repository and P2P recommender systems to mention a few. However, classification in a P2P network is a challenging task due to the constraints such as centralization of data is not feasible, scarce communication bandwidth, scalability, synchronization and peer dynamism. Moreover, without considering data distributions and topological scenarios of real world P2P systems, most of the existing distributed classification approaches lack in their predictive and network-cost performance. In this paper, we investigate a collaborative classification method (TRedSVM) based on Support Vector Machines (SVM) in Scale-free P2P networks. In particular, we demonstrate how to construct SVM classifier in real world P2P networks which exhibit inherently skewed distribution of node links and eventually data. The proposed method propagates the most influential instances of SVM models to the vast majority of scarcely connected peers in a controlled way that improves their local classification accuracy and, at the same time, keeps the communication cost low throughout the network. Besides using benchmark Machine Learning data sets for extensive experimental evaluations, we have evaluated the proposed method particularly for music genre classification to exhibit its performance in a real application scenario. Additionally, performance analysis is carried out with respect to centralized approaches, data replication in P2P networks and cost accuracy trade-off. TRedSVM outperforms baseline approaches of model propagation by improving the overall classification performance substantially at the cost of a tolerable increase in communication.

Musical Genre Classification Using SVM and Audio Features

The need of advance Music Information Retrieval increases as well as a huge amount of digital music files distribution on the internet. Musical genres are the main top-level descriptors used to organize digital music files. Most of work in labeling genre done manually. Thus, an automatic way for labeling a genre to digital music files is needed. The most standard approach to do automatic musical genre classification is feature extraction followed by supervised machine-learning. This research aims to find the best combination of audio features using several kernels of non-linear Support Vector Machines (SVM). The 31 different combinations of proposed audio features are dissimilar compared in any other related research. Furthermore, among the proposed audio features, Linear Predictive Coefficients (LPC) has not been used in another works related to musical genre classiffication. LPC was originally used for speech coding. An experimentation in classifying digital music file into a genre is carried out. The experiments are done by extracting feature sets related to timbre, rhythm, tonality and LPC from music files. All possible combination of the extracted features are classified using three different kernel of SVM classifier that are Radial Basis Function (RBF), polynomial and sigmoid. The result shows that the most appropriate kernel for automatic musical genre classification is polynomial kernel and the best combination of audio features is the combination of musical surface, Mel-Frequency Cepstrum Coefficients (MFFC), tonality and LPC. It achieves 76.6 % in classification accuracy.

Music Genre Classification

The purpose of this research is to build a machine learning model to predict the genre of a song. This paper analyzes a song as a wave and determines the factors involved and predicts the genre. Application of the model is primarily to automatize the process of genre identification which shall aid in building of music recommendation systems.

Using Generic Summarization to Improve Music Information Retrieval Tasks

In order to satisfy processing time constraints, many MIR tasks process only a segment of the whole music signal. This practice may lead to decreasing performance, since the most important information for the tasks may not be in those processed segments. In this paper, we leverage generic summarization algorithms, previously applied to text and speech summarization, to summarize items in music datasets. These algorithms build summaries, that are both concise and diverse, by selecting appropriate segments from the input signal which makes them good candidates to summarize music as well. We evaluate the summarization process on binary and multiclass music genre classification tasks, by comparing the performance obtained using summarized datasets against the performances obtained using continuous segments (which is the traditional method used for addressing the previously mentioned time constraints) and full songs of the same original dataset. We show that GRASSHOPPER, LexRank, LSA, MMR, and a Support Sets-based Centrality model improve classification performance when compared to selected 30-second baselines. We also show that summarized datasets lead to a classification performance whose difference is not statistically significant from using full songs. Furthermore, we make an argument stating the advantages of sharing summarized datasets for future MIR research.

A survey on symbolic data-based music genre classification

Music is present in everyday life and used for a wide range of objectives. Musical databases have considerably increased in number and size over the past years, therefore, the development of accurate tools for music information retrieval (MIR) has become an important topic in computer science. The increasing theoretical advances in machine learning algorithms together with the abundance of recordings available in digital audio formats, the growing quality and accessibility of on-line symbolic music data, and availability of tools and toolboxes for the extraction of musical properties have motivated many studies on machine learning and MIR. Relevant problems in MIR include classification of songs into genres, which enables the summarization of common features (or patterns) shared by different songs. The automatic classification of music genres plays a fundamental role in the context of music indexing and retrieval, so that websites and device music engines can manage and label music content. Most studies have dealt with such an issue by extracting music characteristics from the audio content, and some have provided overviews of audio features and classification algorithms for music genre classification. However, precise high-level musical information can be extracted from symbolic data (e.g. digital music scores), known to be closely related to the way humans perceive music. A number of approaches use such musical information to process, retrieve and classify music content. This manuscript provides an overview of the most important approaches that deal with music genre classification and consider the symbolic representation of music data. Current issues inherent to such a music format, as well the main algorithms adopted for the modeling of the music feature space are presented.

Combining visual and acoustic features for music genre classification

Since musical genre is one of the most common ways used by people for managing digital music databases, music genre recognition is a crucial task, deep studied by the Music Information Retrieval (MIR) research community since 2002. In this work we present a novel and effective approach for automated musical genre recognition based on the fusion of different set of features. Both acoustic and visual features are considered, evaluated, compared and fused in a final ensemble which show classification accuracy comparable or even better than other state-of-the-art approaches. The visual features are locally extracted from sub-windows of the spectrogram taken by Mel scale zoning: the input signal is represented by its spectrogram which is divided in sub-windows in order to extract local features; feature extraction is performed by calculating texture descriptors and bag of features projections from each sub-window; the final decision is taken using an ensemble of SVM classifiers. In this work we show for the first time that a bag of feature approach can be effective in this problem. As the acoustic features are concerned, we propose an ensemble of heterogeneous classifiers for maximizing the performance that could be obtained starting from the acoustic features. First timbre features are obtained from the audio signal, second some statistical measures are calculated from the texture window and the modulation spectrum, third a feature selection is executed to increase the recognition performance and decrease the computational complexity. Finally, the resulting descriptors are classified by fusing the scores of heterogeneous classifiers (SVM and Random subspace of AdaBoost). The experimental evaluation is performed on three well-known databases: the Latin Music Database (LMD), the ISMIR 2004 database and the GTZAN genre collection. The reported performance of the proposed approach is very encouraging, since they outperform other state-of-the-art approaches, without any ad hoc parameter optimization (i.e. using the same ensemble of classifiers and parameters setting in all the three datasets). The advantage of using both visual and audio features is also proved by means of Q-statistics, which confirms that the two sets of features are partially independent and they are suitable to be fused together in a heterogeneous system. The MATLAB code of the ensemble of classifiers and for the visual features extraction will be publicly available (see footnote 1) to other researchers for future comparisons. The code for acoustic features is not available since it is used in a commercial system.

Combining Acoustic and Multilevel Visual Features for Music Genre Classification

Most music genre classification approaches extract acoustic features from frames to capture timbre information, leading to the common framework of bag-of-frames analysis. However, time-frequency analysis is also vital for modeling music genres. This article proposes multilevel visual features for extracting spectrogram textures and their temporal variations. A confidence-based late fusion is proposed for combining the acoustic and visual features. The experimental results indicated that the proposed method achieved an accuracy improvement of approximately 14% and 2% in the world's largest benchmark dataset (MASD) and Unique dataset, respectively. In particular, the proposed approach won the Music Information Retrieval Evaluation eXchange (MIREX) music genre classification contests from 2011 to 2013, demonstrating the feasibility and necessity of combining acoustic and visual features for classifying music genres.

Classification of Music Genre using Neural Networks with Cross-Entropy Optimization and Soft-Max Output

In this paper, an abstract model to predict the genre of a music audio file is proposed (specifically a wave file).The output of the model is the probability distribution along the considered genres. A machine learning approach is employed. The adaptive learning process is modeled by neural networks with back-propagation as its learning algorithm and cross entropy as its optimization function. The emphasis is on feature extractors since the learning paradigm is well known to other applications. Simple Analysis on the Features were performed for appropriate selection. General Terms Music Classification, Optimization Problem.

Music genre classification applied to bass enhancement for mobile technology

The aim of this paper is to present a novel approach to the Virtual Bass Synthesis (VBS) algorithms applied to portable computers. The proposed algorithm is related to intelligent, rule-based setting of synthesis parameters according to music genre of an audio excerpt. The classification of music genres is automatically executed employing MPEG 7 parameters and the Principal Component Analysis method applied to reduce information redundancy. To perform genre recognition k-Nearest Neighbors classifier is used. The VBS algorithm is based on nonlinear device (NLD) or phase vocoder (PV) depending on the content of an audio file excerpt. A soft computing (fuzzy logic) algorithm is employed to set optimum synthesis parameters depending on a given song. To confirm the relationship between genres and preferences of listeners in the low frequency range the pairwise subjective comparison test is carried out. In tests 30 pairs of audio files are employed divided into six popular musical genres. Music excerpts processed by a commercially available bass boost algorithm are used for comparison. Based on the responses of the listeners the statistical analysis is carried out. A short summary is also provided that contains plans for future algorithm development.

Classification of Music Genres Based on Music Separation into Harmonic and Drum Components

Abstract This article presents a study on music genre classification based on music separation into harmonic and drum components. For this purpose, audio signal separation is executed to extend the overall vector of parameters by new descriptors extracted from harmonic and/or drum music content. The study is performed using the ISMIS database of music files represented by vectors of parameters containing music features. The Support Vector Machine (SVM) classifier and co-training method adapted for the standard SVM are involved in genre classification. Also, some additional experiments are performed using reduced feature vectors, which improved the overall result. Finally, results and conclusions drawn from the study are presented, and suggestions for further work are outlined.

Importance of audio feature reduction in automatic music genre classification

Multimedia database retrieval is rapidly growing and its popularity in online retrieval systems is consequently increasing. Large datasets are major challenges for searching, retrieving, and organi...

Music Genre Classification via Joint Sparse Low-Rank Representation of Audio Features

A novel framework for music genre classification, namely the joint sparse low-rank representation (JSLRR) is proposed in order to: 1) smooth the noise in the test samples, and 2) identify the subspaces that the test samples lie onto. An efficient algorithm is proposed for obtaining the JSLRR and a novel classifier is developed, which is referred to as the JSLRR-based classifier. Special cases of the JSLRR-based classifier are the joint sparse representation-based classifier and the low-rank representation-based one. The performance of the three aforementioned classifiers is compared against that of the sparse representation-based classifier, the nearest subspace classifier, the support vector machines, and the nearest neighbor classifier for music genre classification on six manually annotated benchmark datasets. The best classification results reported here are comparable with or slightly superior than those obtained by the state-of-the-art music genre classification methods.

Music Genre Classification using Improved Artificial Neural Network with Fixed Size Momentum

genres are defined as categorical labels that auditors use to characterize pieces of music sample. A musical genre can be characterized by a set of common perceptive parameters. An automatic genre classification would actually be very helpful to replace or complete human genre annotation, which is actually used. Neural networks have found overwhelming success in the area of pattern recognition. The standard back propagation algorithm is used for training network with fixed learning rate. This paper classifies music into genres using improved neural network with fixed size momentum. Finally we validate the proposed algorithm with experimental results of accuracy.

Spatial Audio Player Using Musical Genre Classification

Spatial Audio Player Using Musical Genre Classification

Music genre classification based on local feature selection using a self-adaptive harmony search algorithm

This paper proposes an automatic music genre-classification system based on a local feature-selection strategy by using a self-adaptive harmony search (SAHS) algorithm. First, five acoustic characteristics (i.e., intensity, pitch, timbre, tonality, and rhythm) are extracted to generate an original feature set. A feature-selection model using the SAHS algorithm is then employed for each pair of genres, thereby deriving the corresponding local feature set. Finally, each one-against-one support vector machine (SVM) classifier is fed with the corresponding local feature set, and the majority voting method is used to classify each musical recording. Experiments on the GTZAN dataset were conducted, demonstrating that our method is effective. The results show that the local-selection strategies using wrapper and filter approaches ranked first and third in performance among all relevant methods.

Heuristic ternary error-correcting output codes via weight optimization and layered clustering-based approach.

One important classifier ensemble for multiclass classification problems is error-correcting output codes (ECOCs). It bridges multiclass problems and binary-class classifiers by decomposing multiclass problems to a serial binary-class problems. In this paper, we present a heuristic ternary code, named weight optimization and layered clustering-based ECOC (WOLC-ECOC). It starts with an arbitrary valid ECOC and iterates the following two steps until the training risk converges. The first step, named layered clustering-based ECOC (LC-ECOC), constructs multiple strong classifiers on the most confusing binary-class problem. The second step adds the new classifiers to ECOC by a novel optimized weighted (OW) decoding algorithm, where the optimization problem of the decoding is solved by the cutting plane algorithm. Technically, LC-ECOC makes the heuristic training process not blocked by some difficult binary-class problem. OW decoding guarantees the nonincrease of the training risk for ensuring a small code length. Results on 14 UCI datasets and a music genre classification problem demonstrate the effectiveness of WOLC-ECOC.

A Study on Music Genre Recognition and Classification Techniques

Automatic classification of music genre is widely studied topic in music information retrieval (MIR) as it is an efficient method to structure and organize the large numbers of music files available on the Internet. Generally, the genre classification process of music has two main steps: feature extraction and classification. The first step obtains audio signal information, while the second one classifies the music into various genres according to extracted features. In this paper, we present a study on techniques for automatic music genre recognition and classification. We first describe machine learning based chord recognition methods, such as hidden Markov models, neural networks, dynamic Bayesian network and rule-based methods, and template matching methods. We then explain supervised, unsupervised and semi-supervised classification methods classifying music genres. Finally, we briefly describe the proposed method for automatic classification of music genres, which consists of three steps: chord labeling, genre matching and classification.

Directed Acyclic Graphs for Content Based Sound, Musical Genre, and Speech Emotion Classification

This work introduces the methodology of Decision Directed Acyclic Graphs (DDAG)11 This work uses the following abbreviations as regards to directed graphs: Directed Acyclic Graph (DAG), Decision Directed Acyclic Graph (DDAG) and Directed Acyclic Graph Hidden Markov Model (DAGHMM). to the scientific domain of content based audio signal processing. We apply the particular methodology to three multiclass classification problems involving the categories of generalized sound events, musical genres, and speech expressing emotional states. A decision graph is constructed which breaks the overall problem into a series of two-class ones. The order of the graph nodes is revealed using a clustering criterion based on the Kullback-Leibler divergence. Every graph node is composed by two hidden Markov models, each one representing the class which participates in the specific problem. We extract three heterogeneous feature sets (Mel-Filterbank, MPEG-7 Audio Spectrum Projection and Perceptual Wavelet Packets) out of each recording and fuse them for training the HMMs. Extensive comparative experiments are conducted using the following three datasets: (a) a combination of professional sound effects collections, (b) GTZAN musical genre database, and (c) BERLIN emotional speech corpus. The results demonstrate the superiority of the DDAG classification approach over the standard HMM approach regardless the application task.

Deep Scattering Spectrum

A scattering transform defines a locally translation invariant representation which is stable to time-warping deformation. It extends MFCC representations by computing modulation spectrum coefficients of multiple orders, through cascades of wavelet convolutions and modulus operators. Second-order scattering coefficients characterize transient phenomena such as attacks and amplitude modulation. A frequency transposition invariant representation is obtained by applying a scattering transform along log-frequency. State-the-of-art classification results are obtained for musical genre and phone classification on GTZAN and TIMIT databases, respectively.